Accuracy (pairwise: stronger binder identified within sampled antibody pairs) of Boltz-2 (AlphaBind pairwise evaluation) on AlphaBind PP489 antibody variants (held-out antigen)
55.5% Accuracy (pairwise: stronger binder identified within sampled antibody pairs)
Methods
- Tested configuration
- Boltz-2 (AlphaBind pairwise evaluation)
- Protocol
- AlphaBind PP489 held-out antigen, pairwise accuracy
- Dataset
- AlphaBind PP489 antibody variants (held-out antigen)
- Procedure
- AlphaBind PP489 held-out antigen, pairwise accuracy
- Evaluation
- Boltz-2 on AlphaBind PP489 (pairwise accuracy)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source
- Evidence
- Independent external evaluation · source checkedA systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2, row 'PP489', column 'Boltz-2 - iplddt (%)'; STAR Methods, 'Cross-antigen evaluation setup'
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- Held-out antigen
- Adaptation
- Zero-shot confidence score
- Scoring implementation
- Pairwise accuracy (%) as printed
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 55.52% Individual claims | A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Table 2, row 'PP489', column 'Boltz-2 - iplddt (%)'; STAR Methods, 'Cross-antigen evaluation setup' Version: iScience 2026, 116522; PMC13444443 full-text XML | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-11 independent paper Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsExtraction: Parsed the <td> cells of the pinned PMC XML with extract/extract_mochibind.py; header row asserted. Table 2 body row 2. Independent review 2026-10-11: Re-downloaded the Europe PMC full-text XML and matched its byte count and SHA-256. Parsed every table-wrap of the pinned XML with an independent parser: all 16 Table 2 cells are extracted and the printed string, the numeric accuracy and, for MochiBind, the p-value all match. Table 1 is a feature matrix of prior studies and the key resources table holds no performance values, so neither is extracted; no other table in the XML carries results. All 16 cells, the header row, the footnote and the p-value strings were also read directly from the table markup, which is the whole batch rather than a sample. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Original source · iScience 2026, 116522; PMC13444443 full-text XML
Technical metadata and extraction receipts
Stable ID: lit-interactions-20261011-mochibind-result-boltz-2-pp489
- metric
- accuracy
- metric direction
- higher
- unit
- percent
- printed value
- 55.52%
- source locator
- Table 2, row 'PP489', column 'Boltz-2 - iplddt (%)'; STAR Methods, 'Cross-antigen evaluation setup'
- review
- method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the Europe PMC full-text XML and matched its byte count and SHA-256. Parsed every table-wrap of the pinned XML with an independent parser: all 16 Table 2 cells are extracted and the printed string, the numeric accuracy and, for MochiBind, the p-value all match. Table 1 is a feature matrix of prior studies and the key resources table holds no performance values, so neither is extracted; no other table in the XML carries results. All 16 cells, the header row, the footnote and the p-value strings were also read directly from the table markup, which is the whole batch rather than a sample.; reviewer: claude; reviewer note: Claude review agent reviewer-mi-1, independent of the extractor lit-microbial-interactions; no human review claimed; date: 2026-10-11; artifact sha256: 0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13444443/fullTextXML; note: Extraction: Parsed the <td> cells of the pinned PMC XML with extract/extract_mochibind.py; header row asserted. Table 2 body row 2. Independent review 2026-10-11: Re-downloaded the Europe PMC full-text XML and matched its byte count and SHA-256. Parsed every table-wrap of the pinned XML with an independent parser: all 16 Table 2 cells are extracted and the printed string, the numeric accuracy and, for MochiBind, the p-value all match. Table 1 is a feature matrix of prior studies and the key resources table holds no performance values, so neither is extracted; no other table in the XML carries results. All 16 cells, the header row, the footnote and the p-value strings were also read directly from the table markup, which is the whole batch rather than a sample.
- numeric value
- 55.52
- metric qualifier
- pairwise: stronger binder identified within sampled antibody pairs
- missing metadata
- uncertainty: reason: unreported
Related records
- evaluation: Boltz-2 on AlphaBind PP489 (pairwise accuracy)